Crisp index structures introduce the problem of having sharp decision boundaries which may not be found in the real life clustering problems. In real world, specifically in the CBIR context, each data may not be fully assigned to one cluster and it may partially belong to other clusters, as opposed to the crisp index structures which fully affect data to clusters according to their proximity in terms of distance in the high-dimensional vector space. Based on kernel-fuzzy C-means clustering (KFCM) mechanism, this paper presents a fast and efficient index structure to support high-dimensional indexing for both crisp and fuzzy data. The proposed index structure offers a number of advantages such as a compact and efficient fuzzy data clustering. The experimental study demonstrates the efficiency and effectiveness of our method.