Well, you didn't actually link to it ;) Seriously though, that is a shortcoming of the study. If a member mentions it without the link, it does not count.
You can create a candidate list of titles for those books that do get linked then check for those titles in the body of each comment - not too computationally expensive and embarrassingly parallel.
I hope it's clear that I was not saying that I could have done better. It's a great example of low-hanging fruit. Thank you, Ramiro, for doing this and sharing it with us all.
