Secret messages can be embedded in a webpage by switching the uppercase-lowercase states of letters in tags. In this paper, a novel steganalytic approach called Tag-Mismatch analysis for detection of hidden information embedded in tags is presented. In order to guarantee reasonable false positive and false negative, the approach is firstly trained on a set of 4,100 webpages to determine the decision threshold. It is shown that the length of embedded secret messages can be estimated with relatively high precision and the resulting detection algorithm is simple and fast. The experimental results show that the detection rate is larger than 85%, as the embedded rate is larger than 0.3%.