Abstract: A method of processing data by creating an inverted column index is presented. The method entails categorizing words in documents according to data type, generating a posting list for each of the words that are categorized, and organizing the words in an inverted column index format. In an inverted column index, each column represents a data type, and each of the words is encoded in a key and the posting list is encoded in a value associated with the key. In some cases, the words that are categorized may be the most commonly appearing words arranged in the order of frequency of appearance in each column. This indexing method provides an overview of words that are in a large dataset, allowing a user to choose the words that are of interest to him and “drill down” into contents that include that word by way of queries.