Intelligent query and retrieval techniques from remote sensing archives become more and more important with the increasing number of satellites in orbit recording more and more data. At the same time the increasing resolution of the sensors produces images of higher complexity. To allow easy access to this information, thus to enhanced usage of the data, content-based query techniques are inevitable. In this article we present the structure of a new intelligent remote sensing image archive providing query by image content. First we capture the information in the image using a family of robust signal models which are not selected according to a certain application but instead are able to describe the information in a condensed way. In a next level of information processing the images in the archive are clustered using conjectural models. Finally, the application-oriented user query is answered on a semantic level. In this way, users of various fields of remote sensing applications are able to see their data in the archive.