E-business sites and shopping mall sites deal with a lot of image information. To find a specific image from image sources, we usually use web search engines or image database engines. But, the feature based retrieval capabilities of these systems are quite limited, especially for the web images. This Paper presents Web Image Metadata Mining System For E-business Intelligence. We propose the indexing techniques and color based image classification and representation schemes of user log. The system keeps track of user's preferences by generating user query logs and automatically adds more search information to subsequent user queries. To demonstrate the usefulness of the proposed system, some experimental results showing and precision are also explained.