Abstract: Content-based image retrieval is one of the current active and promising research in image analysis and image management. The work of transfering the results of these research to support images in DBMS has also been initiated by many researchers and commercial systems. In this paper, we first illustrate the importance of using content-based operations in combination with the traditional database operations. Then, we propose an image repository model that supports content-based operations on image databases. Furthermore, we introduce our novel similarity-based operators on image tables and investigate their properties. Finally, we investigate the use of the novel content-based operators in combination with the relational operators on image and relational tables.