Novel content based medical image retrieval based on BoVW classification method

•The proposed Speeded Up Robust Features feature extraction method is three times faster than Scale Invariant Feature Transform. The main advantage of SURF is less time consuming [18].•The advantage of K-means clustering suggested to decide effectively on the seed point set. The clusterings proposed provide for a grouping of similar pixel values [16] (Vamsidhar E: Murthy (2010).•The BoVW classification system used to solve the issue of the SVM classifier process [12]. Visual bag is used for arrangement based on color, size and texture.•The Proposed Spark map reduction approach is used to solve the map reduction problem [12]. Spark map reduction method divides the task into a different block in parallel for fast recovery.•The proposed method used CBIR with BoVW and spark map reduces the process by which high precision and best output results are obtained. Amount of digital image is increasing exponentially nowadays. Storage requirements for these images increase from Gigabytes to Pet bytes. Searching and retrieving the relevant images from such larger volume of images datasets based on its contents plays dynamic role in various applications for computer vision. There are many common retrieval systems are there to provide solutions for this problem. Times taken to retrieve the images are high and accuracy of retrieved images is less in the existing systems. The limitation of Hadoop maps reduce is the lack of performing real time tasks efficiently. A proficient content-based image retrieval framework based on Spark Map Reduce with bag of visual word is to be proposed to perform with high accuracy for big data. The Apache spark programming can be utilized to productively recover pictures with less retrieval time and retrieve the accurate images from the big database that resemble the query image. The proposed system obtained an accuracy of 97.7% and it is better than the existing classification method for Retrieve the image from the large database.