An increasing in quantity of multimedia data brought a new problem that expected data should be retrieved fast and exactly. The adequate representation is a key element for the efficient retrieval. For this reason, MPEG-7 standard was established for description of multimedia data. However, the content of the standard is massive, and the approach method is not clear for real application system yet. In this paper, we suggest implementation scheme of retrieval system with using visual descriptors only, and present the performance results of developed system. From the results of developed system, MPEG-7 VIRS (Video/Image Retrieval System), we analyze the retrieval performances between using the use of individual descriptor and using multiple descriptors, and show a layout for the real application systems.