System and method for suggesting keywords based on image contents

A computer-implemented method includes receiving a first visual media article from an entity that provides content sources, identifying a first content item of the first visual media article, and identifying in a database a second visual media article that includes a second content item, wherein the second content item is substantially similar to the first content item. The method further includes extracting from logging data one or more keywords that yield a listing of a content source that includes the second visual media article, and suggesting the extracted one or more keywords to the entity.